© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 63617
    Prev
    Next
    INDEX
    Explanations

    rewards, points, programs, loyalty

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    çī¹æ´¾
    -0.11
    ter
    -0.09
    åªļ
    -0.08
    çīº
    -0.08
    ä»Ĭ天çļĦ
    -0.08
    _teams
    -0.08
    ää
    -0.08
    ä»Ĭ天
    -0.08
     khÃŃ
    -0.08
    INSTALL
    -0.08
    POSITIVE LOGITS
    å¥ĸåĬ±
    0.11
    没äºĭ
    0.11
    urning
    0.10
    æĸ¥
    0.09
     Lux
    0.09
    ç°ĩ
    0.09
    ensible
    0.09
    æį¢
    0.09
    edic
    0.09
    udem
    0.09
    Activations Density 0.009%

    No Known Activations